Semantic comparison between two document versions. Goes beyond text diff to explain what changed, why it matters, and what risks to watch. Built for contracts, policies, specs, and any versioned document. Outputs a structured change report with risk analysis.
Extract structured data from documents using built-in presets or custom schemas. Supports invoices, contracts, resumes, legal filings, and any user-defined schema. Outputs consistent JSON or CSV. Handles batch processing across multiple files.
Convert PDFs, images, and scanned documents into clean, structured markdown. Extracts text, tables, headings, metadata, and document hierarchy. Handles large documents by chunking intelligently. Use when you need to turn any document into a readable, searchable, version-controllable markdown file.
Ask questions across one or more documents and get cited answers. Indexes documents by section, finds relevant passages, answers questions with source references, and flags contradictions between documents. Works with PDFs, markdown, text, and images.
Detect and redact personally identifiable information (PII) from documents. Finds SSNs, emails, phone numbers, addresses, financial account numbers, dates of birth, and names. Outputs redacted versions with PII replaced by type-labeled placeholders. Supports batch processing.